Modeling unvoiced sounds in statistical parametric speech synthesis with a continuous vocoder.
Tamás Gábor CsapóGéza NémethMilos CernakPhilip N. GarnerPublished in: EUSIPCO (2016)
Keyphrases
- speech synthesis
- speech recognition
- statistical modeling
- text to speech
- statistical analysis
- statistical models
- real time
- prosodic features
- vocal tract
- modeling framework
- modeling language
- speech signal
- statistical methods
- genetic algorithm
- database
- statistical information
- continuous domains
- neural network
- kernel density estimators